def evaluate(self, results, logger=None, **kwargs):
"""Evaluate the results.
Args:
results (list[list | tuple]): Testing results of the dataset.
logger (logging.Logger | str | None): Logger used for printing
related information during evaluation. Default: None.
Returns:
dict[str: float]: AP results of the total dataset or each separate
dataset if `self.separate_eval=True`.
"""
assert len(results) == self.cumulative_sizes[-1], \
('Dataset and results have different sizes: '
f'{self.cumulative_sizes[-1]} v.s. {len(results)}')
# Check whether all the datasets support evaluation
for dataset in self.datasets:
assert hasattr(dataset, 'evaluate'), \
f'{type(dataset)} does not implement evaluate function'
if self.separate_eval: # 大部分是这个场景
dataset_idx = -1
total_eval_results = dict()
for size, dataset in zip(self.cumulative_sizes, self.datasets):
start_idx = 0 if dataset_idx == -1 else \
self.cumulative_sizes[dataset_idx]
end_idx = self.cumulative_sizes[dataset_idx + 1]
results_per_dataset = results[start_idx:end_idx]
print_log(
f'\nEvaluateing {dataset.ann_file} with '
f'{len(results_per_dataset)} images now',
logger=logger)
eval_results_per_dataset = dataset.evaluate(
results_per_dataset, logger=logger, **kwargs)
dataset_idx += 1
for k, v in eval_results_per_dataset.items():
total_eval_results.update({f'{dataset_idx}_{k}': v})
return total_eval_results
elif any([isinstance(ds, CocoDataset) for ds in self.datasets]):
raise NotImplementedError(
'Evaluating concatenated CocoDataset as a whole is not'
' supported! Please set "separate_eval=True"')
elif len(set([type(ds) for ds in self.datasets])) != 1:
raise NotImplementedError(
'All the datasets should have same types')
else:
# 多份数据预测结果，一起评估，很少用
original_data_infos = self.datasets[0].data_infos
self.datasets[0].data_infos = sum(
[dataset.data_infos for dataset in self.datasets], [])
eval_results = self.datasets[0].evaluate(results,
logger=logger,
**kwargs)
self.datasets[0].data_infos = original_data_infos
return eval_results
def init_weights(self, pretrained=None):
"""Initialize the weights in detector.
Args:
pretrained (str, optional): Path to pre-trained weights.
Defaults to None.
"""
if pretrained is not None:
logger = get_root_logger()
print_log(f'load model from: {pretrained}', logger=logger)
def evaluate(self,
results,
metric='bbox',
logger=None,
jsonfile_prefix=None,
classwise=False,
proposal_nums=(100, 300, 1000),
iou_thrs=np.arange(0.5, 0.96, 0.05)):
"""Evaluation in COCO protocol.
Args:
results (list): Testing results of the dataset.
metric (str | list[str]): Metrics to be evaluated.
logger (logging.Logger | str | None): Logger used for printing
related information during evaluation. Default: None.
jsonfile_prefix (str | None): The prefix of json files. It includes
the file path and the prefix of filename, e.g., "a/b/prefix".
If not specified, a temp file will be created. Default: None.
classwise (bool): Whether to evaluating the AP for each class.
proposal_nums (Sequence[int]): Proposal number used for evaluating
recalls, such as recall@100, recall@1000.
Default: (100, 300, 1000).
iou_thrs (Sequence[float]): IoU threshold used for evaluating
recalls. If set to a list, the average recall of all IoUs will
also be computed. Default: 0.5.
Returns:
dict[str: float]
"""
metrics = metric if isinstance(metric, list) else [metric]
allowed_metrics = ['bbox', 'segm', 'proposal', 'proposal_fast']
for metric in metrics:
if metric not in allowed_metrics:
raise KeyError(f'metric {metric} is not supported')
result_files, tmp_dir = self.format_results(results, jsonfile_prefix)
eval_results = {}
cocoGt = self.coco
for metric in metrics:
msg = f'Evaluating {metric}...'
if logger is None:
msg = '\n' + msg
print_log(msg, logger=logger)
if metric == 'proposal_fast':
ar = self.fast_eval_recall(results,
proposal_nums,
iou_thrs,
logger='silent')
log_msg = []
for i, num in enumerate(proposal_nums):
eval_results[f'AR@{num}'] = ar[i]
log_msg.append(f'\nAR@{num}\t{ar[i]:.4f}')
log_msg = ''.join(log_msg)
print_log(log_msg, logger=logger)
continue
if metric not in result_files:
raise KeyError(f'{metric} is not in results')
try:
cocoDt = cocoGt.loadRes(result_files[metric])
except IndexError:
print_log('The testing results of the whole dataset is empty.',
logger=logger,
level=logging.ERROR)
break
iou_type = 'bbox' if metric == 'proposal' else metric
cocoEval = COCOeval(cocoGt, cocoDt, iou_type)
cocoEval.params.catIds = self.cat_ids
cocoEval.params.imgIds = self.img_ids
if metric == 'proposal':
cocoEval.params.useCats = 0
cocoEval.params.maxDets = list(proposal_nums)
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
metric_items = [
'AR@100', 'AR@300', 'AR@1000', 'AR_s@1000', 'AR_m@1000',
'AR_l@1000'
]
for i, item in enumerate(metric_items):
val = float(f'{cocoEval.stats[i + 6]:.3f}')
eval_results[item] = val
else:
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
if classwise: # Compute per-category AP
# Compute per-category AP
# from https://github.com/facebookresearch/detectron2/
precisions = cocoEval.eval['precision']
# precision: (iou, recall, cls, area range, max dets)
assert len(self.cat_ids) == precisions.shape[2]
results_per_category = []
for idx, catId in enumerate(self.cat_ids):
# area range index 0: all area ranges
# max dets index -1: typically 100 per image
nm = self.coco.loadCats(catId)[0]
precision = precisions[:, :, idx, 0, -1]
precision = precision[precision > -1]
if precision.size:
ap = np.mean(precision)
else:
ap = float('nan')
results_per_category.append(
(f'{nm["name"]}', f'{float(ap):0.3f}'))
num_columns = min(6, len(results_per_category) * 2)
results_flatten = list(
itertools.chain(*results_per_category))
headers = ['category', 'AP'] * (num_columns // 2)
results_2d = itertools.zip_longest(*[
results_flatten[i::num_columns]
for i in range(num_columns)
])
table_data = [headers]
table_data += [result for result in results_2d]
table = AsciiTable(table_data)
print_log('\n' + table.table, logger=logger)
metric_items = [
'mAP', 'mAP_50', 'mAP_75', 'mAP_s', 'mAP_m', 'mAP_l'
]
for i in range(len(metric_items)):
key = f'{metric}_{metric_items[i]}'
val = float(f'{cocoEval.stats[i]:.3f}')
eval_results[key] = val
ap = cocoEval.stats[:6]
eval_results[f'{metric}_mAP_copypaste'] = (
f'{ap[0]:.3f} {ap[1]:.3f} {ap[2]:.3f} {ap[3]:.3f} '
f'{ap[4]:.3f} {ap[5]:.3f}')
if tmp_dir is not None:
tmp_dir.cleanup()
return eval_results
def print_map_summary(mean_ap,
results,
dataset=None,
scale_ranges=None,
logger=None):
"""Print mAP and results of each class.
A table will be printed to show the gts/dets/recall/AP of each class and
the mAP.
Args:
mean_ap (float): Calculated from `eval_map()`.
results (list[dict]): Calculated from `eval_map()`.
dataset (list[str] | str | None): Dataset name or dataset classes.
scale_ranges (list[tuple] | None): Range of scales to be evaluated.
logger (logging.Logger | str | None): The way to print the mAP
summary. See `mmdet.utils.print_log()` for details. Default: None.
"""
if logger == 'silent':
return
if isinstance(results[0]['ap'], np.ndarray):
num_scales = len(results[0]['ap'])
else:
num_scales = 1
if scale_ranges is not None:
assert len(scale_ranges) == num_scales
num_classes = len(results)
recalls = np.zeros((num_scales, num_classes), dtype=np.float32)
aps = np.zeros((num_scales, num_classes), dtype=np.float32)
num_gts = np.zeros((num_scales, num_classes), dtype=int)
for i, cls_result in enumerate(results):
if cls_result['recall'].size > 0:
recalls[:, i] = np.array(cls_result['recall'], ndmin=2)[:, -1]
aps[:, i] = cls_result['ap']
num_gts[:, i] = cls_result['num_gts']
if dataset is None:
label_names = [str(i) for i in range(num_classes)]
elif mmdet.cv_core.is_str(dataset):
label_names = get_classes(dataset)
else:
label_names = dataset
if not isinstance(mean_ap, list):
mean_ap = [mean_ap]
header = ['class', 'gts', 'dets', 'recall', 'ap']
for i in range(num_scales):
if scale_ranges is not None:
print_log(f'Scale range {scale_ranges[i]}', logger=logger)
table_data = [header]
for j in range(num_classes):
row_data = [
label_names[j], num_gts[i, j], results[j]['num_dets'],
f'{recalls[i, j]:.3f}', f'{aps[i, j]:.3f}'
]
table_data.append(row_data)
table_data.append(['mAP', '', '', '', f'{mean_ap[i]:.3f}'])
table = AsciiTable(table_data)
table.inner_footing_row_border = True
print_log('\n' + table.table, logger=logger)